The research proposes NoiseAttack, a novel backdoor attack for image classification that utilizes the power spectral density (PSD) of White Gaussian Noise (WGN) to achieve imperceptibility and robustness.  The WGN trigger is embedded globally across all training samples but designed to activate only on specific target samples. NoiseAttack achieves sample-specific multi-targeted misclassification, allowing the attacker … Continue reading NoiseAttack: The Backdoor Using Power Spectral Density for Stealthy Evasion